dc.contributor.editor | Varela Vaca, Ángel Jesús | es |
dc.contributor.editor | Ceballos Guerrero, Rafael | es |
dc.contributor.editor | Reina Quintero, Antonia María | es |
dc.creator | Perales Gómez, Ángel Luis | es |
dc.creator | Fernández Maimó, Lorenzo | es |
dc.creator | Huertas Celdrán, Alberto | es |
dc.creator | García Clemente, Félix J. | es |
dc.date.accessioned | 2024-07-18T10:03:12Z | |
dc.date.available | 2024-07-18T10:03:12Z | |
dc.date.issued | 2024 | |
dc.identifier.citation | Perales Gómez, Á.L., Fernández Maimó, L., Huertas Celdrán, A. y García Clemente, F.J. (2024). A Review of VAASI: Crafting Valid and Abnormal Adversarial Samples for Anomaly Detection Systems in Industrial Scenarios [Póster]. En Jornadas Nacionales de Investigación en Ciberseguridad (JNIC) (9ª.2024. Sevilla) (452-453), Sevilla: Universidad de Sevilla. Escuela Técnica Superior de Ingeniería Informática. | |
dc.identifier.isbn | 978-84-09-62140-8 | es |
dc.identifier.uri | https://hdl.handle.net/11441/161508 | |
dc.description.abstract | Existing adversarial attacks are not feasible in industrial scenarios since they primarly deals with continuous features and not with categorical features. To enhance cyber security in industrial settings, this paper introduces an inno vative adversarial attack approach tailored specifically to these environments. This novel technique allows for the creation of targeted adversarial samples valid within supervised cyberattack detection models in industrial scenarios, maintaining consistency of discrete values and correcting cases where adversarial samples appear normal. Validation involved assessing mean error and total adversarial samples generated, comparing against the Projected Gradient Descent method and Carlini & Wagner attack across various parameter configurations. Our proposal achieved the best balance between mean error and generated adversarial samples, demonstrating its superiority. | es |
dc.format | application/pdf | es |
dc.format.extent | 2 | es |
dc.language.iso | eng | es |
dc.publisher | Universidad de Sevilla. Escuela Técnica Superior de Ingeniería Informática | es |
dc.relation.ispartof | Jornadas Nacionales de Investigación en Ciberseguridad (JNIC) (9ª.2024. Sevilla) (2024), pp. 452-453. | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Adversarial attacks | es |
dc.subject | Anomaly detection | es |
dc.subject | Deep learning | es |
dc.subject | Explainable artificial intelligence | es |
dc.subject | Industrial systems | es |
dc.title | A Review of VAASI: Crafting Valid and Abnormal Adversarial Samples for Anomaly Detection Systems in Industrial Scenarios [Póster] | es |
dc.type | info:eu-repo/semantics/conferenceObject | es |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.publication.initialPage | 452 | es |
dc.publication.endPage | 453 | es |
dc.eventtitle | Jornadas Nacionales de Investigación en Ciberseguridad (JNIC) (9ª.2024. Sevilla) | es |
dc.eventinstitution | Sevilla | es |
dc.relation.publicationplace | Sevilla | es |